summaryrefslogtreecommitdiff
path: root/searx/engines/digg.py
diff options
context:
space:
mode:
authorThomas Pointhuber <thomas.pointhuber@gmx.at>2015-01-09 21:25:13 +0100
committerThomas Pointhuber <thomas.pointhuber@gmx.at>2015-01-09 21:30:09 +0100
commit400b54191c590663f0cfe91045f70a5d9223aa19 (patch)
tree08c71466ac8fbaf69872f114847baec762f5bd81 /searx/engines/digg.py
parentaf8dac93a8acff5042b7b399c38e348f0bdc32ad (diff)
parentc8be128e97479ea6c871c4b6fbf014fa8136e708 (diff)
Merge branch 'master' of https://github.com/asciimoo/searx into code_results
Conflicts: searx/engines/searchcode_code.py searx/engines/searchcode_doc.py searx/static/oscar/js/searx.min.js searx/templates/oscar/result_templates/default.html searx/templates/oscar/result_templates/images.html searx/templates/oscar/result_templates/map.html searx/templates/oscar/result_templates/torrent.html searx/templates/oscar/result_templates/videos.html
Diffstat (limited to 'searx/engines/digg.py')
-rw-r--r--searx/engines/digg.py70
1 files changed, 70 insertions, 0 deletions
diff --git a/searx/engines/digg.py b/searx/engines/digg.py
new file mode 100644
index 000000000..8c457d6b9
--- /dev/null
+++ b/searx/engines/digg.py
@@ -0,0 +1,70 @@
+## Digg (News, Social media)
+#
+# @website https://digg.com/
+# @provide-api no
+#
+# @using-api no
+# @results HTML (using search portal)
+# @stable no (HTML can change)
+# @parse url, title, content, publishedDate, thumbnail
+
+from urllib import quote_plus
+from json import loads
+from lxml import html
+from cgi import escape
+from dateutil import parser
+
+# engine dependent config
+categories = ['news', 'social media']
+paging = True
+
+# search-url
+base_url = 'https://digg.com/'
+search_url = base_url+'api/search/{query}.json?position={position}&format=html'
+
+# specific xpath variables
+results_xpath = '//article'
+link_xpath = './/small[@class="time"]//a'
+title_xpath = './/h2//a//text()'
+content_xpath = './/p//text()'
+pubdate_xpath = './/time'
+
+
+# do search-request
+def request(query, params):
+ offset = (params['pageno'] - 1) * 10
+ params['url'] = search_url.format(position=offset,
+ query=quote_plus(query))
+ return params
+
+
+# get response from search-request
+def response(resp):
+ results = []
+
+ search_result = loads(resp.text)
+
+ if search_result['html'] == '':
+ return results
+
+ dom = html.fromstring(search_result['html'])
+
+ # parse results
+ for result in dom.xpath(results_xpath):
+ url = result.attrib.get('data-contenturl')
+ thumbnail = result.xpath('.//img')[0].attrib.get('src')
+ title = ''.join(result.xpath(title_xpath))
+ content = escape(''.join(result.xpath(content_xpath)))
+ pubdate = result.xpath(pubdate_xpath)[0].attrib.get('datetime')
+ publishedDate = parser.parse(pubdate)
+
+ # append result
+ results.append({'url': url,
+ 'title': title,
+ 'content': content,
+ 'template': 'videos.html',
+ 'publishedDate': publishedDate,
+ 'thumbnail': thumbnail})
+
+ # return results
+ return results